Home / Current Issue / Paper 1715449
AI-Powered Automated Behavioral Mock Interview System with Star-Based Evaluation and Leadership Scoring
Subject area: Science,Engineering and Technology · Area of research: Artificial Intelligence and Automation
Abstract
This paper presents an AI-powered Interview Bot, a real-time conversational platform designed to automate and enhance the interview process using advanced speech recognition and language models. Traditional interview systems rely heavily on manual evaluation and lack scalability and consistency in candidate assessment. The proposed system integrates WebRTC-based audio capture, WebSocket-based real-time streaming, and AI-driven evaluation models to conduct dynamic and interactive interviews. Audio inputs from candidates are processed using Deepgram for speech-to-text conversion, while Groq-powered large language models analyze responses based on structured evaluation metrics such as scoring, leadership assessment, and STAR-based feedback. The system also incorporates resume parsing using PDF processing techniques to provide contextual questioning. Real-time feedback is continuously updated on the dashboard, enabling immediate performance insights. By combining real-time communication, AI evaluation, and scalable architecture, the system provides an efficient, automated, and intelligent solution for modern recruitment processes.
Keywords
AI Interview Bot; Speech-to-Text; WebRTC; WebSocket; Deepgram; Groq LLM; Resume Parsing; Real-Time Processing; Automated Evaluation; Candidate Scoring; NLP; Conversational AI
References
[1] B. Schuller, S. Steidl, and A. Batliner, "The INTERSPEECH 2009 Emotion Challenge," in Proc. INTERSPEECH, 2009, pp. 312–315.
[2] D. Jurafsky and J. H. Martin, "Speech and Language Processing," 3rd ed., Pearson Education, 2021.
[3] T. Brown et al., "Language Models are Few-Shot Learners," in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), 2020, pp. 1877–1901.
[4] A. Graves, A. Mohamed, and G. Hinton, "Speech Recognition with Deep Recurrent Neural Networks," in Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP), 2013, pp. 6645–6649.
[5] Y. LeCun, Y. Bengio, and G. Hinton, "Deep Learning," Nature, vol. 521, no. 7553, pp. 436–444, 2015.
[6] E. Cambria, B. Schuller, Y. Xia, and C. Havasi, "New Avenues in Opinion Mining and Sentiment Analysis," IEEE Intelligent Systems, vol. 28, no. 2, pp. 15–21, 2013.
[7] R. Cowie, E. Douglas-Cowie, and C. Cox, "Emotion Recognition in Human-Computer Interaction," IEEE Signal Processing Magazine, vol. 18, no. 1, pp. 32–80, 2001.
[8] S. Poria, E. Cambria, and A. Gelbukh, "Deep Convolutional Neural Network Textual Features and Multiple Kernel Learning for Multimodal Sentiment Analysis," in Proc. EMNLP, 2015, pp. 2539–2544.
How to cite this paper
@article{1715449,
author = {Kayalvizhi.S , Dr. K. Ponmozhi },
title = {AI-Powered Automated Behavioral Mock Interview System with Star-Based Evaluation and Leadership Scoring},
journal = {Iconic Research And Engineering Journals},
year = {2026},
volume = {9},
number = {9},
pages = {2066-2074},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1715449.pdf},
abstract = {This paper presents an AI-powered Interview Bot, a real-time conversational platform designed to automate and enhance the interview process using advanced speech recognition and language models. Traditional interview systems rely heavily on manual evaluation and lack scalability and consistency in candidate assessment. The proposed system integrates WebRTC-based audio capture, WebSocket-based real-time streaming, and AI-driven evaluation models to conduct dynamic and interactive interviews. Audio inputs from candidates are processed using Deepgram for speech-to-text conversion, while Groq-powered large language models analyze responses based on structured evaluation metrics such as scoring, leadership assessment, and STAR-based feedback. The system also incorporates resume parsing using PDF processing techniques to provide contextual questioning. Real-time feedback is continuously updated on the dashboard, enabling immediate performance insights. By combining real-time communication, AI evaluation, and scalable architecture, the system provides an efficient, automated, and intelligent solution for modern recruitment processes.},
keywords = {AI Interview Bot; Speech-to-Text; WebRTC; WebSocket; Deepgram; Groq LLM; Resume Parsing; Real-Time Processing; Automated Evaluation; Candidate Scoring; NLP; Conversational AI},
month = {March},
doi = {https://doi.org/10.64388/IREV9I9-1715449}
}